Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "v_proj",
     "o_proj",
-    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
     "down_proj",
-    "k_proj"
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005c4b1ba0a1c6f022b3b1f7c9a5c439a8e62a590e07ff936a99b410efbd3b71
+oid sha256:a261c336a146b145d7f5266ea1c4e9507e1aade18fa9911075ec040f5f0baebd
 size 608249904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3facc065bac14415921a3c6e2ddd0198a74a54c5bf87e6f02b4058ae08d46f1
+oid sha256:fe450567d18eee2c6567302d0846c1cb483805d9d9177b8d7e407f4a59f4c215
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:3d52f4c790365904b81e5bc1ca0ff3c1655ec4153c08229cbe7a73da5731820c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,27 +1,35 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1111111111111111,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.3333333333333333,
+  "eval_steps": 2,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.1111111111111111,
-      "eval_loss": 1.6721346378326416,
-      "eval_runtime": 0.3562,
-      "eval_samples_per_second": 11.228,
-      "eval_steps_per_second": 5.614,
+      "eval_loss": 1.5672025680541992,
+      "eval_runtime": 0.357,
+      "eval_samples_per_second": 11.204,
+      "eval_steps_per_second": 5.602,
       "step": 1
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "eval_loss": 1.5623606443405151,
+      "eval_runtime": 0.3589,
+      "eval_samples_per_second": 11.146,
+      "eval_steps_per_second": 5.573,
+      "step": 2
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 9,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 3,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 262900618887168.0,
+  "total_flos": 788701856661504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518ada41d7be532dc2ada99b97fabc3eaa774bec604b48644d23ebab09d04ac6
+oid sha256:8b01544fc3fb587621705972ed0c544c1c853e12dd1fd269413d7c12758ee68a
 size 6776